Calibration

Vals SWE-bench → AA-SciCode

Name: benchgap: LLM benchmark scores, measured and estimated
Creator: benchgap

AA-SciCode is estimated from Vals SWE-bench with a linear curve fitted on 42 models measured on both: y = 0.3738·x + 0.2117, R² = 0.47, cross-validated error 4.3 pp. It is used for 1 estimate.

Estimated model	Vals SWE-bench	AA-SciCode	Source
Qwen3.5 Flash	64.4%	45.2%	estimated ± 4.3 pp, medium confidence